Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing

TL;DR

This paper evaluates deep learning models for detecting military radars in 3.5 GHz spectrograms, demonstrating that neural networks outperform classical methods and can effectively analyze large spectral datasets.

Contribution

It introduces a deep learning approach for radar detection in the 3.5 GHz band and compares its performance to traditional methods using a large spectrogram dataset.

Findings

Deep learning models outperform classical detection methods.

A three-layer CNN balances accuracy and computational efficiency.

The approach reveals weaknesses in classical detection techniques.

Abstract

In the United States, the Federal Communications Commission has adopted rules permitting commercial wireless networks to share spectrum with federal incumbents in the 3.5~GHz Citizens Broadband Radio Service band. These rules require commercial systems to vacate the band when sensors detect radars operated by the U.S. military; a key example being the SPN-43 air traffic control radar. Such sensors require highly-accurate detection algorithms to meet their operating requirements. In this paper, using a library of over 14,000 3.5~GHz band spectrograms collected by a recent measurement campaign, we investigate the performance of thirteen methods for SPN-43 radar detection. Namely, we compare classical methods from signal detection theory and machine learning to several deep learning architectures. We demonstrate that machine learning algorithms appreciably outperform classical signal detection methods. Specifically, we find that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity. Last, we apply this three-layer network to generate descriptive statistics for the full 3.5~GHz spectrogram library. Our findings highlight potential weaknesses of classical methods and strengths of modern machine learning algorithms for radar detection in the 3.5~GHz band.